Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44015
    Prev
    Next
    INDEX
    Explanations

    protection and security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demikian
    -0.08
    (ok
    -0.08
    BTN
    -0.08
     terdapat
    -0.08
     Federation
    -0.08
     recently
    -0.08
    .Must
    -0.08
     continents
    -0.07
    LX
    -0.07
     Motto
    -0.07
    POSITIVE LOGITS
     harmful
    0.12
     pitfalls
    0.11
     جلوگیری
    0.11
     danos
    0.10
     excessive
    0.10
     prevenir
    0.10
     Prevention
    0.10
     tyranny
    0.10
     unwanted
    0.10
     prevention
    0.10
    Activations Density 0.103%

    No Known Activations